Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1334039 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1098554 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.4230. Min Act: -0.0001

Data Index: 364275 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.4192. Min Act: -0.0001

Data Index: 256446 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3430. Min Act: -0.0001

Data Index: 669420 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3643. Min Act: -0.0001

Data Index: 430720 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3517. Min Act: -0.0001

Data Index: 246154 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3370. Min Act: -0.0001

Data Index: 1268655 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3194. Min Act: -0.0001

Data Index: 887528 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3063. Min Act: -0.0001

Data Index: 454034 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3258. Min Act: -0.0001

Data Index: 449010 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1119976 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2983. Min Act: -0.0001

Data Index: 1352444 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1196174 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2970. Min Act: -0.0001

Data Index: 416597 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2706. Min Act: -0.0001

Data Index: 663124 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2860. Min Act: -0.0001

Data Index: 722623 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2603. Min Act: -0.0001

Data Index: 288202 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.2781. Min Act: -0.0001

Data Index: 803162 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.4849. Min Range: -0.4849

Max Act: 0.3141. Min Act: -0.0001

Data Index: 75056 (C4 (Web Text))

Max Activating Token Index: 215